Certifiably robust interpretation via Rényi differential privacy
- Ao Liu
- Xiaoyu Chen
- et al.
- 2022
- Artificial Intelligence
Paper
Publications
960 results for Trustworthy AI
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
- Dennis Wei
- Rahul Nair
- et al.
- 2022
- NeurIPS 2022
Conference paperLogical Credal Networks
- Radu Marinescu
- Haifeng Qian
- et al.
- 2022
- NeurIPS 2022
Conference paperFair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
- Prasanna Sattigeri
- Soumya Ghosh
- et al.
- 2022
- NeurIPS 2022
Conference paperAccelerating Certified Robustness Training via Knowledge Transfer
- Pratik Vaishnavi
- Kevin Eykholt
- et al.
- 2022
- NeurIPS 2022
Conference paperCalibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
- Songkai Xue
- Yuekai Sun
- et al.
- 2022
- NeurIPS 2022
Conference paperk-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension
- Ziv Goldfeld
- Kristjan Greenewald
- et al.
- 2022
- NeurIPS 2022
PosterConsistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions
- Chanakya Ekbote
- Moksh Jain
- et al.
- 2022
- NeurIPS 2022
Workshop paperVerifiable Federated Learning
- Simone Bottoni
- Giulio Zizzo
- et al.
- 2022
- NeurIPS 2022
Workshop paperVisual Prompting for Adversarial Robustness
- Aochuan Chen
- Peter Lorenz
- et al.
- 2022
- NeurIPS 2022
Workshop paper